Artificial Intelligence in COVID-19, Procedural Medicine and Cancer

人工智能在 COVID-19、程序医学和癌症中的应用

• 批准号: 10920178
• 负责人: Bradford Wood
• 金额: --
• 依托单位: CLINICAL CENTER
• 依托单位国家: 美国
• 资助国家: 美国
• 起止时间: 至
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10920178
• 关键词: 3-Dimensional; 3D Print; Algorithms; Angiography; Antibodies; Artificial Intelligence; Atelectasis; Bacterial Pneumonia; Biological Markers; COVID-19; COVID-19 detection; COVID-19 pandemic; COVID-19 patient; Cellular Phone; Classification; Clinical; Clinical Trials; Coagulation Process; Collaborations; Communicable Diseases; Communication; Computer software; Critical Care; Custom; Data; Data Science; Data Set; Detection; Development; Devices; Disease; Disease Outbreaks; Disease Outcome; Epidemiology; Event; Future; Goals; Hearing Tests; Home; Image; Industry; Infection; Institution; Institutional Review Boards; Interventional radiology; Investigation; Knowledge; Language; Learning; Link; Lung; Lung diseases; Malignant Neoplasms; Masks; Measures; Medical; Medical Imaging; Medical Research; Medicine; Methodology; Methods; Modality; Modeling; National Center for Advancing Translational Sciences; National Institute of Allergy and Infectious Disease; National Institute of Biomedical Imaging and Bioengineering; Nature; Oxygen; Oxygen saturation measurement; Pathway interactions; Patients; Pattern; Performance; Phenotype; Postoperative Period; Postpartum Period; Pre-Clinical Model; Prevention; Privacy; Privatization; Publishing; Reporting; Research Personnel; Resources; Running; Signal Transduction; Social Distance; Source; Standardization; Starvation; Suggestion; Techniques; Testing; Text; The Cancer Imaging Archive; Thoracic Radiography; Training; Triage; United States National Institutes of Health; Vasculitis; Ventilator; Voice; Weight; X-Ray Computed Tomography; cancer invasiveness; chest computed tomography; clinical imaging; coronavirus disease; data sharing; deep learning; deep learning model; design; disease classification; drug discovery; federated learning; flu; forging; fungal pneumonia; health care settings; image guided therapy; image processing; in vivo; influenza pneumonia; large datasets; migration; minimally invasive; multidisciplinary; multimodality; novel; outcome prediction; pandemic disease; point of care; post-COVID-19; public-private partnership; response; skills; smartphone application; smartphone based device; social media; tool; transfer learning; wearable device; working group

A multidisciplinary multi-institute, public-private partnership tackled the goal of developing and validating AI tools and standardized methodologies for clinical dynamics and novel classification tools for medical imaging, voice analysis, data sharing, and detection and prevention of dynamic diseases. A public pipeline for classification of COVID-19 (vs Flu) on chest CT was deployed. The NIH and extended team were among the first to gather multi-national data and develop freeware public AI solutions based on COVID CTs for academic, researcher, and commercial developer use. A uniform and standardized methodology for automatic classification of disease based on imaging, voice spectrograms, text input, or information from wearables could expedite the pathway towards drug discovery, infection outbreak and migration, and non-invasive quantification of disease such as vasculitis, post-operative clots or atelectasis. The NIH team developed and helped publicly post COVID-19 data and tools on TCIA and MIDRC, including the largest (summer 2020) chest CT dataset posted for the 1st year of the pandemic. NVIDIA and NIH co-developed AI models that detected COVID-19, differentiated from influenza, fungal, or bacterial pneumonias as well as other entities. AI models were able to predict the later need for critical care therapies based upon an initial CT scan early on, at the initial point of care. The public-private multinational partnership also used "federated learning" to train an AI model in 8 nations and 20 institutions that was able to predict subsequent oxygen needs based upon the initial point-of-care chest X-ray alone (Nature Medicine). This demonstrated methodology for data collaboration protects while maintaining privacy and allowing the data itself to remain at the home institution. Federated learning can in this way overcome shortcomings in unbalanced source data for AI, by sharing "model weights" instead of the actual data. This enabling technique overcome data sharing gaps, thus showing that the data does not need to be fully shared, in order to build quality AI models from medical imaging. The team also showed that CT AI can track disease in a predictable fashion in the pre-symptomatic, asymptomatic, and pauci-symptomatic patient, and that the general dynamic curve of disease has dynamic curve lab correlates may be predictive and recapitulate available preclinical models. Correlation with zip codes or cell phone towers could theoretically predict disease outbreak and migration patterns. CT image processing and deep learning models provide quantifiable metrics to serve as a noninvasive biomarkers for pulmonary involvement in COVID-19. A MICCAI AI data challenge in COVID-19 was organized around the data that the team curated. The NIH multi-national dataset (>3000 CTs /4 nations) showed that CT may be positive days before PCR. Thus, the suggestion that CT could function as a targeted epidemiological tool to perhaps augment PCR and antibody testing in specific limited scenarios or better define patterns of spread. Early signal for Omicron correlatives also led to development of a classification model purely from voice audiograms / spectrograms with high performance metrics, which was not true for Alpha and Delta. Partnerships with the Trans-NIH working group has been forged, including NIAID IRF, NIBIB MIDCR, NCI, NCATS, and N3C. Centralized communication and discovery pathways for COVID-19-related data science that involves medical imaging like CT or chest x-ray is a common theme and goal, and provides a fertile ground for advancement of data science with broad scope impact in cancer and in interventional radiology and well outside of infectious diseases. NIH participated in publishing and disseminating methods for handling COVID-19 in the angiography suite, details about post-partum COVID, designed and characterized a disposable isolation device ("full body mask") that reduces contamination in health care settings such as transport of COVID positive patients, validated in vivo a miniature 3D printable ventilator for resource-starved pandemic settings, and deployed a camera with custom software to identify social distancing distances with a standard webcam. A clinical trial for training AI models for Omicron detection from public social media audio data was IRB approved. Smartphone tools for instant anonynmization of imaging data were developed. A smartphone app for point-of-care deployment was created for running inference on clinical PACS 2D imaging or for cloud transmittal. Further collaborations with N3C, industry, Oxford and IRF NIAID were developed for assessment of AI tools with PPG, wearables, and smartphone apps.

多学科、多机构、公私合作伙伴关系的目标是开发和验证用于临床动态的人工智能工具和标准化方法，以及用于医学成像、语音分析、数据共享以及动态疾病检测和预防的新型分类工具。部署了用于胸部 CT 上的 COVID-19（与流感）分类的公共管道。 NIH 和扩展团队是第一批收集跨国数据并开发基于新冠病毒 CT 的免费软件公共人工智能解决方案的机构之一，供学术界、研究人员和商业开发人员使用。基于成像、语音频谱图、文本输入或可穿戴设备信息的统一和标准化的疾病自动分类方法可以加快药物发现、感染爆发和迁移以及血管炎、感染后疾病等疾病的非侵入性量化的进程。手术血栓或肺不张。 NIH 团队开发并帮助在 TCIA 和 MIDRC 上公开发布 COVID-19 数据和工具，包括大流行第一年发布的最大（2020 年夏季）胸部 CT 数据集。 NVIDIA 和 NIH 共同开发了可检测 COVID-19 的 AI 模型，该模型与流感、真菌或细菌性肺炎以及其他实体区分开来。 AI 模型能够根据早期护理点的初始 CT 扫描来预测后续对重症护理治疗的需求。这一公私跨国合作伙伴关系还使用“联邦学习”在 8 个国家和 20 个机构中训练人工智能模型，该模型能够仅根据最初的护理点胸部 X 光检查（《自然医学》）来预测随后的氧气需求。这种经过验证的数据协作方法可以在保护隐私的同时保护隐私，并允许数据本身保留在本地机构。联邦学习可以通过共享“模型权重”而不是实际数据来克服人工智能源数据不平衡的缺点。这种支持技术克服了数据共享差距，从而表明数据不需要完全共享，即可从医学成像构建高质量的人工智能模型。 研究小组还表明，CT AI 可以以可预测的方式追踪症状前、无症状和少症状患者的疾病，并且疾病的一般动态曲线具有动态曲线实验室相关性，可以预测并概括可用的临床前模型。理论上，与邮政编码或手机信号塔的相关性可以预测疾病的爆发和迁移模式。 CT 图像处理和深度学习模型提供了可量化的指标，可作为 COVID-19 肺部受累的无创生物标志物。 COVID-19 中的 MICCAI AI 数据挑战赛是围绕团队整理的数据组织的。 NIH 多国数据集（> 3000 个 CT/4 个国家）显示 CT 可能在 PCR 前几天呈阳性。因此，建议 CT 可以作为一种有针对性的流行病学工具，以在特定的有限情况下增强 PCR 和抗体检测或更好地定义传播模式。 Omicron 相关产品的早期信号还导致了纯粹根据具有高性能指标的语音听力图/声谱图的分类模型的开发，但这对于 Alpha 和 Delta 来说并非如此。 与 Trans-NIH 工作组建立了合作伙伴关系，包括 NIAID IRF、NIBIB MIDCR、NCI、NCATS 和 N3C。涉及 CT 或胸部 X 光等医学成像的 COVID-19 相关数据科学的集中通信和发现途径是一个共同的主题和目标，并为数据科学的进步提供了肥沃的土壤，在癌症和介入领域具有广泛的影响放射学和传染病之外的疾病。 NIH 参与发布和传播了在血管造影套件中处理 COVID-19 的方法、有关产后 COVID 的详细信息，设计并描述了一次性隔离装置（“全身面罩”），该装置可减少医疗机构中的污染，例如 COVID 的运输阳性患者在体内验证了微型 3D 打印呼吸机适用于资源匮乏的大流行环境，并部署了带有定制软件的摄像头，以通过标准网络摄像头识别社交距离。一项用于训练 AI 模型以从公共社交媒体音频数据进行 Omicron 检测的临床试验已获得 IRB 批准。开发了用于图像数据即时匿名化的智能手机工具。创建了用于现场护理部署的智能手机应用程序，用于在临床 PACS 2D 成像上运行推理或用于云传输。与 N3C、工业界、牛津大学和 IRF NIAID 进一步合作，通过 PPG、可穿戴设备和智能手机应用程序评估人工智能工具。